renzrollon/interlock
Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.
field: unknown workflow: Testing & TDDPlanning & specsPR / code reviewGit & commitsDocs runs claude in CI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit renzrollon/interlock/.claude ./rig-interlock # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit renzrollon/interlock/skills/bootstrap .claude/skills/bootstrap $ npx degit renzrollon/interlock/skills/commit .claude/skills/commit $ npx degit renzrollon/interlock/skills/dispatch .claude/skills/dispatch $ npx degit renzrollon/interlock/skills/docs-digest .claude/skills/docs-digest $ npx degit renzrollon/interlock/skills/evals .claude/skills/evals $ npx degit renzrollon/interlock/skills/explain-code .claude/skills/explain-code $ npx degit renzrollon/interlock/skills/explore .claude/skills/explore $ npx degit renzrollon/interlock/skills/fix-tests .claude/skills/fix-tests $ npx degit renzrollon/interlock/skills/graph .claude/skills/graph $ npx degit renzrollon/interlock/skills/manual-test-plan .claude/skills/manual-test-plan $ npx degit renzrollon/interlock/skills/report .claude/skills/report $ npx degit renzrollon/interlock/skills/review-artifacts .claude/skills/review-artifacts $ npx degit renzrollon/interlock/skills/review-code .claude/skills/review-code $ npx degit renzrollon/interlock/skills/settle .claude/skills/settle $ npx degit renzrollon/interlock/skills/ship .claude/skills/ship $ npx degit renzrollon/interlock/skills/spec .claude/skills/spec
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (16)
bootstrapcommitdispatchdocs-digestevalsexplain-codeexplorefix-testsgraphmanual-test-planreportreview-artifactsreview-codesettleshipspec
Permissions
deny (0)
—
ask (0)
—
allow (9)
Bash(interlock:*)
Bash(interlock-graph:*)
Bash(openspec:*)
Bash(git:*)
Bash(npm test:*)
Bash(node --test:*)
Bash(test:*)
Bash(printenv:*)
Bash(mkdir:*)
Similar rigs
Zamaniego/claude-code-setup
—
Fort Knox 1.0k tok · · Q28
bmmmm/claudii
Statusline for Claude Code — session cost, context %, rate limits and model health in your shell prompt. Zero daemons, pure bash+jq.
Minimalist 1.8k tok · · Q15
Kibertum/tausik-core
AI coding agents can't quietly fake "done". Signed ed25519 receipts prove the gates actually ran — bound to the commit, verifiable offline. Fail-closed hooks block the edit, not the PR. Harness engineering over Claude Code, Cursor, Codex, Q
Skill Collector 1.7k tok · · Q3
epicsagas/epic-harness
Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, autonomous spec-to-PR pipeline. Works with Claude Code, Codex, Cursor, OpenCode, and Cline.
Skill Collector 6.1k tok · · Q3